We release Evo-RL, the opensource real-world offline RL on So-101 and AgileX PiPER for easier reproduction.

The unitree_il_lerobot open-source project is a modification of the LeRobot open-source training framework, enabling the training and testing of data collected using the dual-arm dexterous hands of…

TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics

Being-H is BeingBeyond's family of human-centric embodied foundation models.

A Pragmatic VLA Foundation Model

[CVPR 2026] Official implementation of "Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation"

[L4DC 2026] "FALCON: Learning Force-Adaptive Humanoid Loco-Manipulation"

MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots

Real-Time VLAs via Future-state-aware Asynchronous Inference.

TextOp: Real-time Interactive Text-Driven Humanoid Robot Motion Generation and Control

Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t, Gr0…

[ICRA 2026] VITRA: Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos

[arXiv 2025] TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System

Code for "ACG: Action Coherence Guidance for Flow-based Vision-Language-Action Models" (ICRA 2026)

RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

[ICLR 2026] The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model"

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

MLA: A Multisensory Language-Action Model for Multimodal Understanding and Forecasting in Robotic Manipulation

SLAM-Former: Putting SLAM into One Transformer

Official code of RDT 2

Open GVL

[arXiv 2025] VisualMimic: Visual Humanoid Loco-Manipulation via Motion Tracking and Generation

Official code for PDP

Q-chunking RL for pi0

Building General-Purpose Robots Based on Embodied Foundation Model

[NeurIPS 2025] CogVLA: Cognition-Aligned Vision-Language-Action Models via Instruction-Driven Routing & Sparsification